© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 31498
    Prev
    Next
    INDEX
    Explanations

    file paths and urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¼ĹæīĢåij¨çŁ¥
    -0.06
    gether
    -0.06
    亦åı¯
    -0.06
    ä¸ĭéĿ¢çļĦ
    -0.06
    ä»İèĢĮ
    -0.06
    uzzi
    -0.06
    è¿Ļæĸ¹éĿ¢çļĦ
    -0.06
    ä¹ĸ
    -0.06
    åĭĩå¾Ģ缴åīį
    -0.06
    xx
    -0.05
    POSITIVE LOGITS
    ↵
    0.09
    idget
    0.08
    zelt
    0.08
    转载请注æĺİåĩºå¤Ħ
    0.08
    è¯Ľä»Ļ
    0.08
    ickl
    0.08
    åħ®
    0.08
     ÎŃγι
    0.07
    casts
    0.07
    iring
    0.07
    Activations Density 0.102%

    No Known Activations